Multilayer feedforward networks are universal approximators
Neural Networks
Optimization: algorithms and consistent approximations
Optimization: algorithms and consistent approximations
Smooth function approximation using neural networks
IEEE Transactions on Neural Networks
Neural smooth function approximation and prediction with adaptive learning rate
Transactions on Computational Collective Intelligence VII
| Hi-index | 0.00 |
An algebraic approach for representing multidimensional non-linear functions by feedforward neural networks is implemented for the approximation of smooth batch data containing input-output of the hidden neurons and the final neural output of the network. The training set is associated to the adjustable parameters of the network by weight equations. Then we have obtained the exact input weight of the nonlinear equations and the approximated output weight of the linear equations using the conjugate gradient method with an adaptive learning rate. Using a multi-agents system as different kinds of energies for the plant growth, one can predict the height of the plant.